{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/discriminative-neural-sentence-modeling-by","title":"Discriminative Neural Sentence Modeling by Tree-Based Convolution","arxiv_id":"1504.01106","date":"2015-04-05","proceeding":"EMNLP 2015 9","authors":["Lili Mou","Hao Peng","Ge Li","Yan Xu","Lu Zhang","Zhi Jin"],"abstract":"This paper proposes a tree-based convolutional neural network (TBCNN) for\ndiscriminative sentence modeling. Our models leverage either constituency trees\nor dependency trees of sentences. The tree-based convolution process extracts\nsentences' structural features, and these features are aggregated by max\npooling. Such architecture allows short propagation paths between the output\nlayer and underlying feature detectors, which enables effective structural\nfeature learning and extraction. We evaluate our models on two tasks: sentiment\nanalysis and question classification. In both experiments, TBCNN outperforms\nprevious state-of-the-art results, including existing neural networks and\ndedicated feature/rule engineering. We also make efforts to visualize the\ntree-based convolution process, shedding light on how our models work.","url_abs":"http://arxiv.org/abs/1504.01106v5","url_pdf":"http://arxiv.org/pdf/1504.01106v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-classification-on-trec-6","task":"Text Classification","dataset":"TREC-6","model":"TBCNN","rank_in_archive_order":8,"of":19,"metrics":{"Error":"4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}